Fragility, robustness and antifragility in deep learning

DOI10.1016/J.ARTINT.2023.104060MaRDI QIDQ6152676zbMATH OpenOpenAlexFDO

Authors Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha

Publication date 13 February 2024

Published in Artificial Intelligence (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2312.09821

zbMATH Keywords

robustness analysisdeep neural networksadversarial attacksadversarial robustnessadversarial trainingnetwork sparsity

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Probabilistic robustness estimates for feed-forward neural networks
• Noise sensitivity and stability of deep neural networks for binary classification
• Adversarial noise attacks of deep learning architectures: stability analysis via sparse-modeled signals
• Understanding adversarial robustness via critical attacking route
• Analysis of classifiers' robustness to adversarial perturbations

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Deep double descent: where bigger models and more data hurt*
• Mathematical definition, mapping, and detection of (anti)fragility

This page was built for publication: Fragility, robustness and antifragility in deep learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6152676)